experiment: llm_directed_hpc
kind: llm_directed
seed: 1
n_replicates: 1

# Scaled directed-sex run for an L40S (48 GB). At 7B the uniform soup already composes (0.87, beating
# every specialist), so the sharp question is whether SEARCHING the recombination-weight space +
# selecting on the verifier can push past even that strong a-priori blend — i.e. does offspring
# selection still add headroom once fusion is already strong? Reuses the cached 7B specialists.

base_model: Qwen/Qwen2.5-7B-Instruct
families: [lists, strings, arith]
n_train: 800          # only if cached specialists are absent (fresh on the node)
n_val: 100
n_test: 200
n_candidates: 24
concentration: 0.5
epochs: 3
lora: {r: 16, alpha: 32}

output: {dir: results/llm_directed_hpc}